AI-powered social robots are increasingly discussed as a way to improve the in-store customer experience, but the effects of similarity-based personalization remain unclear. This study examines whether language-based similarity features in a retail recommendation dialogue improve user comfort, trust, and intention to use. In a controlled laboratory experiment, participants interacted with the social robot Furhat either in a basic “good sales assistant” or in an adaptive, similarity-based variant (speech rate, volume, pitch and similarity statements). Questionnaire data and continuous electrodermal activity (EDA) were combined to capture both self-reported and physiological responses. Using robust mean comparisons (Yuen tests), structural equation modeling (SEM) and EDA analyses, no significant differences between conditions in terms of comfort, trust or intention to use were found. However, SEM revealed stable internal mechanisms: rapport strongly predicted comfort, usefulness strongly predicted trust and comfort predicted intention to use. These results suggest that general similarity matching in early social robot interactions in retail is not reliably beneficial. In retail sales consulting, it seems sensible to leave robot behavior unadjusted and to base it on a generally good sales consultant. Improvement through personalization is not generally advantageous but it depends heavily on the context.

This study aims to investigate the influence of two interaction designs on user comfort and intention to use during pre-interaction phase. As part of a field experiment in a retail bank, a proactive and a passive interaction design of a social robot were compared. A standardized questionnaire was used to determine how the interaction design affects the comfort, trust and usage intention of customers and what role trust plays as a mediating factor. The data analysis shows that the proactive design was rated better in terms of psychological comfort and emotional value, but not in terms of trust and intention to use. Comfort with robots positively influenced the intention to use the social robot, with trust serving as a key mediator; in the proactive variant, the effect was only indirect via trust, while in the passive variant, both direct and indirect effects were observed. According to dual processing theory, proactive designs rely on automatic, emotion-driven processes that directly influence comfort, while passive designs encourage reflective decision-making, supporting trust and increasing usage intention despite lower comfort. A balanced integration of both approaches can enhance customer comfort and trust, facilitating the successful adoption of social robots in retail.